Pressure swing adsorption control method and device and pressure swing adsorption control system

Abstract

The invention provides a pressure swing adsorption control method, a pressure swing adsorption control device and a pressure swing adsorption control system. The method comprises the steps that a hydrogen purity difference value is obtained, and the hydrogen purity difference value is the difference value between actual hydrogen purity and target hydrogen purity; determining target pressure swing adsorption time by adopting an APC algorithm and an RTO algorithm at least according to the hydrogen purity difference value; and controlling the pressure swing adsorption device to operate according to the target pressure swing adsorption time. According to the scheme, the problems of low product gas purity and unstable yield caused by low accuracy rate of pressure swing adsorption time in the prior art are solved.

Description

Technical Field

[0001] The present application relates to the field of adsorption control technology, and in particular to a pressure swing adsorption control method, device, computer program product and pressure swing adsorption control system. Background Art

[0002] The current pressure swing adsorption control adsorption regeneration time is manually set based on experience. When the PSA tail gas intake flow and pressure and the content of components (H2, N2, CH4, CO2, CO) in the hydrogen production tail gas are constantly changing and the filtration performance of the adsorption tower is weakened, the cycle time and regeneration time are manually set. However, the adsorption time of this method is often not accurate, which will lead to problems such as low product gas purity and unstable yield, affecting the separation effect and production efficiency. Summary of the invention

[0003] The main purpose of the present application is to provide a pressure swing adsorption control method, device, computer program product and pressure swing adsorption control system to at least solve the problem of low accuracy of pressure swing adsorption time in the prior art, resulting in low purity of product gas and unstable yield.

[0004] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a pressure swing adsorption control method is provided, comprising: obtaining a hydrogen purity difference, wherein the hydrogen purity difference is the difference between an actual hydrogen purity and a target hydrogen purity; determining a target pressure swing adsorption time using an APC algorithm and an RTO algorithm at least based on the hydrogen purity difference; and controlling the operation of a pressure swing adsorption device according to the target pressure swing adsorption time.

[0005] Optionally, before obtaining the hydrogen purity difference, the method also includes: obtaining relevant information, wherein the relevant information includes one or more of permeate gas flow rate, intake pressure and gas composition; constructing a first determination model, wherein the first determination model is trained using multiple sets of training data, each set of training data in the multiple sets of training data includes historical relevant information obtained within a historical time period, and historical target hydrogen purity corresponding to the historical relevant information; inputting the relevant information into the first determination model to obtain the target hydrogen purity corresponding to the relevant information.

[0006] Optionally, at least based on the hydrogen purity difference, an APC algorithm and an RTO algorithm are used to determine a target pressure swing adsorption time, including: obtaining an initial pressure swing adsorption time; and based on the initial pressure swing adsorption time, the hydrogen purity difference and the target hydrogen purity, using an APC algorithm and an RTO algorithm to determine the target pressure swing adsorption time.

[0007] Optionally, according to the initial pressure swing adsorption time, the hydrogen purity difference and the target hydrogen purity, the target pressure swing adsorption time is determined by using an APC algorithm and an RTO algorithm, including: constructing a second determination model, wherein the second determination model is obtained by training with an APC algorithm and an RTO algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes a historical initial pressure swing adsorption time, a historical hydrogen purity difference, a historical target hydrogen purity, and a historical target pressure swing adsorption time corresponding to the historical initial pressure swing adsorption time, the historical hydrogen purity difference, and the historical target hydrogen purity; inputting the initial pressure swing adsorption time, the hydrogen purity difference and the target hydrogen purity into the second determination model to obtain the initial pressure swing adsorption time, the hydrogen purity difference and the target pressure swing adsorption time corresponding to the target hydrogen purity.

[0008] Optionally, after obtaining the initial pressure swing adsorption time, the method further includes: obtaining multiple initial time periods, wherein the initial time period is a partial time period in the initial pressure swing adsorption time; obtaining a minimum initial time period among the multiple initial time periods; adjusting the minimum initial time period to increase the length of the minimum initial time period to obtain a first target time period, wherein the first target time period is a partial time period in the target pressure swing adsorption time.

[0009] Optionally, after obtaining the initial pressure swing adsorption time, the method further includes: obtaining a maximum initial time period among multiple initial time periods; adjusting the maximum initial time period to reduce the length of the maximum initial time period to obtain a second target time period, wherein the second target time period is a partial time period in the target pressure swing adsorption time.

[0010] Optionally, after obtaining the initial pressure swing adsorption time, the method further includes: constructing a third determination model, wherein the third determination model is trained using multiple sets of training data through an APC algorithm, an RTO algorithm and an optimization algorithm, each set of training data in the multiple sets of training data includes a historical initial pressure swing adsorption time, a historical hydrogen purity difference, and a historical target hydrogen purity, the historical initial pressure swing adsorption time, the historical hydrogen purity difference, and the historical target hydrogen purity corresponding to the historical target pressure swing adsorption time, and the optimization algorithm at least includes a genetic algorithm and / or a particle swarm optimization algorithm; the initial pressure swing adsorption time, the hydrogen purity difference and the target hydrogen purity are input into the third determination model to obtain the initial pressure swing adsorption time, the hydrogen purity difference and the target pressure swing adsorption time corresponding to the target hydrogen purity.

[0011] According to another aspect of the present application, a pressure swing adsorption control device is provided, comprising: a first acquisition unit, used to acquire a hydrogen purity difference, wherein the hydrogen purity difference is the difference between an actual hydrogen purity and a target hydrogen purity; a determination unit, used to determine a target pressure swing adsorption time by using an APC algorithm and an RTO algorithm at least based on the hydrogen purity difference; and a control unit, used to control the operation of the pressure swing adsorption device according to the target pressure swing adsorption time.

[0012] According to another aspect of the present application, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the steps of any one of the pressure swing adsorption control methods are implemented.

[0013] According to another aspect of the present application, a pressure swing adsorption control system is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a control method for executing any one of the pressure swing adsorption methods.

[0014] By applying the technical solution of the present application, the time of pressure swing adsorption can be determined by combining the APC algorithm and the RTO algorithm. The APC algorithm is a multivariable optimization algorithm that can perform precise control and reduce errors. The RTO algorithm can be optimized in real time to ensure that the strategy remains in the optimal state. Therefore, the combination of the APC algorithm and the RTO algorithm can improve the accuracy of decision-making, thereby obtaining the accurate time of pressure swing adsorption, thereby improving the purity of the product and making the recovery rate more stable. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0016] Figure 1 A hardware structure block diagram of a mobile terminal for executing a pressure swing adsorption control method provided in an embodiment of the present application is shown;

[0017] Figure 2 A schematic flow chart of a pressure swing adsorption control method provided according to an embodiment of the present application is shown;

[0018] Figure 3 shows a schematic diagram for determining the purity of hydrogen;

[0019] Figure 4 A schematic diagram of the control scheme of APC+RTO is shown;

[0020] Figure 5A structural block diagram of a pressure swing adsorption control device provided according to an embodiment of the present application is shown.

[0021] The above drawings include the following reference numerals:

[0022] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0023] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] As introduced in the background technology, the accuracy of the time of pressure swing adsorption in the prior art is low, resulting in low purity of the product gas and unstable yield. To solve the above problems, the embodiments of the present application provide a pressure swing adsorption control method, device, computer program product and pressure swing adsorption control system.

[0027] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0028] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a pressure swing adsorption control method according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0029] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the display method of device information in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0030] In this embodiment, a control method for pressure swing adsorption running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] Figure 2 FIG. 1 is a flow chart of a pressure swing adsorption control method according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0032] Step S201, obtaining a hydrogen purity difference, wherein the hydrogen purity difference is a difference between an actual hydrogen purity and a target hydrogen purity;

[0033] Specifically, in this scheme, real-time hydrogen purity, i.e., actual hydrogen purity, can be collected. A target hydrogen purity, i.e., the purity of hydrogen achieved under ideal conditions, is preset. By calculating the difference between the actual hydrogen purity and the target hydrogen purity, the hydrogen purity difference is obtained.

[0034] Step S202, determining a target pressure swing adsorption time by using an APC algorithm and an RTO algorithm at least according to the above hydrogen purity difference;

[0035] Specifically, the APC algorithm (Adaptive Proportional Control) is an adaptive proportional control algorithm used to adjust the control parameters of the system to achieve system stability and performance. The algorithm dynamically adjusts the control parameters based on the real-time feedback information of the system, so that the system can quickly respond to changes in the input signal and remain stable.

[0036] The RTO algorithm (Retransmission Timeout) is an algorithm used in the Transmission Control Protocol (TCP) to determine the retransmission timeout of a data packet. In the TCP protocol, after the sender sends a data packet, it will wait for a certain period of time to receive the corresponding confirmation information. If the confirmation information is not received within the timeout period, the data packet will be considered lost and retransmitted. The RTO algorithm dynamically adjusts the retransmission timeout according to the network delay and jitter to improve the efficiency and reliability of data transmission.

[0037] Combining the APC algorithm and the RTO algorithm can achieve real-time optimization control of the pressure swing adsorption time, improve the stability, performance and efficiency of the system, reduce production costs, and realize the automation and intelligence of the system.

[0038] Step S203, controlling the operation of the pressure swing adsorption device according to the target pressure swing adsorption time.

[0039] Specifically, the operation of the pressure swing adsorption device is controlled according to the obtained accurate target pressure swing adsorption time. Since the target pressure swing adsorption time is relatively accurate, the efficiency of the pressure swing adsorption device during operation is also higher.

[0040] Through this embodiment, the time of pressure swing adsorption can be determined by combining the APC algorithm and the RTO algorithm. The APC algorithm is a multivariable optimization algorithm that can perform precise control and reduce errors. The RTO algorithm can be optimized in real time to ensure that the strategy remains in the optimal state. Therefore, the combination of the APC algorithm and the RTO algorithm can improve the accuracy of decision-making, thereby obtaining an accurate time for pressure swing adsorption, thereby improving the purity of the product and making the recovery rate more stable.

[0041] A pressure swing adsorption device is a device used for separation and purification of gases or liquids, which is achieved by adsorbing and desorbing components on the surface of an adsorbent. Common pressure swing adsorption devices include:

[0042] Pressure swing adsorption device: It utilizes the different adsorption properties of adsorbents for different components at different pressures to achieve separation and purification by alternating the pressure of adsorption and desorption.

[0043] Pressure swing desorption adsorption device: Based on the pressure swing adsorption device, the pressure swing in the desorption process is added to improve the separation efficiency.

[0044] Temperature swing adsorption device: It utilizes the different adsorption properties of adsorbents for different components at different temperatures, and achieves separation and purification by alternating the adsorption and desorption temperatures.

[0045] Pressure-Temperature Swing Adsorption Device: Combines changes in pressure and temperature to achieve more efficient separation and purification.

[0046] Adsorption tower: It is a common pressure swing adsorption device, which usually includes a tower body filled with adsorbent and equipment for controlling pressure and temperature changes.

[0047] Specifically, this solution can monitor the hydrogen purity, pressure, intake flow rate of the adsorption tower and the content of gas components (H2, N2, CH4, CO2, CO) in real time, and dynamically adjust the cycle time and parameters of the PSA (Pressure Swing Adsorption) adsorbent to control the cycle time and regeneration time of the pressure swing adsorption device, thereby achieving an efficient pressure swing adsorption process and improving the purity and yield of the product gas. The advantages are that it can improve hydrogen production efficiency, reduce energy consumption, reduce costs, improve product quality, achieve quasi-unmanned operation, improve production intelligence, and reduce the labor intensity of workers.

[0048] In order to further accurately determine the target hydrogen purity, before obtaining the hydrogen purity difference, the method further includes the following steps: obtaining relevant information, wherein the relevant information includes one or more of permeate gas flow rate, inlet pressure and gas composition; constructing a first determination model, wherein the first determination model is trained using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical relevant information obtained within a historical time period and historical target hydrogen purity corresponding to the historical relevant information; inputting the relevant information into the first determination model to obtain the target hydrogen purity corresponding to the relevant information.

[0049] In this scheme, machine learning training can be performed based on the permeate gas flow rate, intake pressure and gas composition to obtain a first determination model, and the first determination model can be used to more accurately determine the target hydrogen purity corresponding to the permeate gas flow rate, intake pressure and gas composition.

[0050] Specifically, the content of components such as (H2, N2, CH4, CO2, CO) in the tail gas of hydrogen production by pressure swing adsorption is changing all the time. In terms of establishing the prediction model, a large number of historical trends are analyzed and screened, abnormal factors such as abnormal faults are marked and processed, and the reaction mechanism and experience are used to assist in the judgment, so that the establishment of the model is practical and adaptable. The main characteristic parameters used in the model include permeate flow rate, pressure, changes in H2, N2, CH4, CO2, and CO components, etc., and the purity of synthetic hydrogen, effective gas components, etc. are used as optimization target parameters.

[0051] Based on the preprocessing and feature extraction of historical production process data, a deep recurrent neural network is used to discover and extract the time-lag relationship model between data changes and tail gas flow and components (i.e., the first determination model). Then, the time-lag relationship model is used to predict the hydrogen purity and pressure swing adsorption time a few minutes or even tens of minutes from the current moment based on the real-time operating conditions. The optimization control system adjusts the PSA adsorption time in time according to the prediction results. The model prediction control scheme is as follows: Figure 3 shown.

[0052] Specifically, the permeate flow rate refers to the gas flow rate that permeates through the adsorbent, which is usually expressed as the volume of gas that passes through the adsorbent per unit time, in units of standard cubic meters per hour or standard cubic meters per minute. The size of the permeate flow rate affects the rate and efficiency of the adsorption process.

[0053] Specifically, the inlet pressure refers to the pressure of the gas entering the adsorber, which is usually expressed in absolute pressure, with the unit of Pascal (Pa) or atmospheric pressure (atm). The size of the inlet pressure affects the adsorption rate and equilibrium state of the gas during the adsorption process.

[0054] Specifically, gas composition refers to the content ratio of various components in a gas mixture, usually expressed as a percentage or mole fraction. Different gas compositions will affect the adsorption selectivity and separation effect of the adsorbent for various gases. During the pressure swing adsorption process, changes in gas composition will affect the permeate flow rate and the purity of the product gas.

[0055] The permeate flow rate refers to the gas flow rate that permeates through the adsorbent. The purity of hydrogen is affected by the permeate flow rate. Generally, the greater the permeate flow rate, the higher the hydrogen purity, because more hydrogen can pass through the adsorbent without being adsorbed.

[0056] Inlet pressure refers to the pressure of the gas entering the adsorber. The size of the inlet pressure will affect the adsorption rate and equilibrium state of the gas during the adsorption process. The higher the inlet pressure, the lower the purity of the hydrogen may be, because high pressure will increase the phenomenon of non-ideal adsorption.

[0057] Gas composition refers to the content ratio of various components in a gas mixture. Different gas compositions will affect the adsorption selectivity and separation effect of the adsorbent for various gases. The purity of hydrogen is directly related to the gas composition. If the hydrogen content in the gas composition is higher, the purity of hydrogen obtained through the adsorption process will also increase accordingly.

[0058] For example, in the pressure swing adsorption process, the inlet pressure is 2atm, the volume fraction of hydrogen is 50%, and the permeate flow rate is 100 standard cubic meters per hour. When the permeate flow rate increases to 200 standard cubic meters per hour, the purity of hydrogen can be increased to 60%. This shows that the increase in permeate flow rate has a positive effect on the purity of hydrogen.

[0059] In addition, the first determination model may be constructed by using a specific algorithm, such as a SVM algorithm, an ANN algorithm, a decision tree algorithm, and a random forest algorithm. Of course, any existing feasible algorithm may also be used.

[0060] Support Vector Machine (SVM): SVM is a supervised learning algorithm suitable for classification and regression problems. By constructing a suitable kernel function, SVM can effectively handle high-dimensional data and nonlinear relationships, and has a high accuracy in predicting hydrogen purity.

[0061] Artificial Neural Network (ANN): ANN is a structure that mimics the interconnection between neurons in the human brain and can be used to establish a model of nonlinear mapping relationships. By training the neural network, the purity of hydrogen can be predicted.

[0062] Decision Tree: A decision tree is an algorithm for making decisions based on a tree structure and is suitable for classification and regression problems. Decision trees are easy to understand and interpret and can help determine the key factors that affect hydrogen purity in the pressure swing adsorption process.

[0063] Random Forest: Random Forest is an ensemble learning algorithm that improves prediction accuracy by building a forest of multiple decision trees and integrating the results of multiple models. Random Forest is suitable for processing multiple variables and large amounts of data.

[0064] In the specific implementation process, the target pressure swing adsorption time is determined by using the APC algorithm and the RTO algorithm at least according to the above-mentioned hydrogen purity difference, which can be achieved by the following steps: obtaining the initial pressure swing adsorption time; determining the above-mentioned target pressure swing adsorption time by using the APC algorithm and the RTO algorithm according to the above-mentioned initial pressure swing adsorption time, the above-mentioned hydrogen purity difference and the above-mentioned target hydrogen purity.

[0065] In this solution, APC can be optimized and controlled to further solve the problem that the current pressure swing adsorption control adsorption regeneration time is manually set based on experience. Based on the precise and reliable control solution of APC+RTO, the adsorption time is obtained, the edge control of hydrogen quality is achieved, and the hydrogen recovery rate is further improved.

[0066] Specifically, this solution realizes fully automatic advanced control of the pressure swing adsorption time through advanced control methods such as multivariable model predictive control and real-time online optimization technology, achieves rapid tracking of PSA intake volume and components, eliminates the lag, inaccuracy and instability caused by existing systems and manual operations, and performs "double optimization" optimal control of the hydrogen production and effective gas components recovered by pressure swing adsorption. This solution predicts the changes in exhaust components by establishing a prediction model through a neural network in terms of a given value of the adsorption time.

[0067] In the specific implementation process, the target pressure swing adsorption time is determined by using the APC algorithm and the RTO algorithm according to the initial pressure swing adsorption time, the hydrogen purity difference and the target hydrogen purity, which can be achieved by the following steps: constructing a second determination model, wherein the second determination model is obtained by training with the APC algorithm and the RTO algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes the historical initial pressure swing adsorption time, the historical hydrogen purity difference, the historical target hydrogen purity, and the historical target pressure swing adsorption time corresponding to the historical initial pressure swing adsorption time, the historical hydrogen purity difference and the historical target hydrogen purity; inputting the initial pressure swing adsorption time, the hydrogen purity difference and the target hydrogen purity into the second determination model to obtain the target pressure swing adsorption time corresponding to the initial pressure swing adsorption time, the hydrogen purity difference and the target hydrogen purity.

[0068] In this scheme, the APC algorithm is a multivariable optimization algorithm that can perform precise control and reduce errors. The RTO algorithm can perform real-time optimization to ensure that the strategy remains in the optimal state. Therefore, this scheme adopts a combination of the APC algorithm and the RTO algorithm to perform machine learning training to obtain a second determination model. The second determination model can be used to more accurately determine the target pressure swing adsorption time.

[0069] Specifically, based on the establishment of the prediction model, the real-time online optimization technology (RTO) is used to find a set of optimal control point settings that match the current gas composition and have global optimal characteristics. After effectiveness verification, the optimal control point setting combination is passed to the APC control system to complete real-time optimization and optimized closed-loop control, so that the pressure swing adsorption time is always kept at the most reasonable. The main adsorption time calculation RTO+APC control scheme is as follows Figure 4 As shown, Figure 4 A pressure swing adsorption hydrogen production optimization control method APC+RTO optimization control diagram is provided. For the above-mentioned automatic optimization control of PSA time, hydrogen purity is used as the target value, and the deviation between the hydrogen purity PV and the set hydrogen purity SP is used as the input 1 of the advance control model. The previously optimized total adsorption time T is used as the input 2 of the advance control model (i.e., the initial pressure swing adsorption time). The hydrogen purity + feedforward model predicted by the neural network prediction model is used as the input 3 of the advance control model (i.e., the target hydrogen purity obtained by the first determination model). At the same time, the total adsorption time of PSA is adjusted and optimized in real time and allocated to the time distribution model through the hand operator.

[0070] Specifically, the initial PSA time refers to the initial time set when the adsorption process begins, which is usually used in the startup and commissioning phase of the adsorption system. A short initial PSA time may result in hydrogen purity lower than the target value, while a long initial PSA time may result in a waste of energy and resources.

[0071] Specifically, the hydrogen purity difference refers to the difference between the actual hydrogen purity and the target hydrogen purity. The size of the hydrogen purity difference reflects the quality of the hydrogen separation effect during the adsorption process, and the goal is to make the hydrogen purity as close to the set target value as possible.

[0072] Specifically, the target hydrogen purity is the desired hydrogen purity value set during the adsorption process, which is usually determined by production requirements or product specifications. The setting of the target hydrogen purity will affect the operation and regulation of the entire adsorption process.

[0073] Specifically, the target PSA time is the adsorption time set to achieve the target hydrogen purity, and is reasonably planned based on actual production needs and adsorption system performance. The setting of the target PSA time will affect the achievement of hydrogen purity and production efficiency.

[0074] For example, the initial PSA time is 10 minutes, the target hydrogen purity is 90%, the hydrogen purity difference is 5%, and the target PSA time is 20 minutes. After actual operation and adjustment, it is found that the actual hydrogen purity is 85%, which is 5% different from the target hydrogen purity. In order to achieve the target purity, the adsorption time needs to be extended to 30 minutes. This shows that the initial PSA time is short, resulting in the hydrogen purity failing to reach the target value, and the target PSA time needs to be adjusted to achieve the target hydrogen purity.

[0075] The APC algorithm is used to monitor and adjust the operating parameters of the pressure swing adsorption process in real time to ensure that the system operates within the set target range. The APC algorithm can optimize and adjust parameters such as inlet pressure and permeate flow rate based on real-time data and feedback information to improve hydrogen purity and production efficiency.

[0076] The RTO algorithm is used to optimize the operating strategy and parameter settings in the pressure swing adsorption process in real time to achieve the best production effect. The RTO algorithm is usually combined with mathematical optimization methods to optimize the model of the adsorption system to determine the optimal operating strategy and parameter settings to maximize hydrogen purity or minimize production costs.

[0077] Specifically, the APC algorithm can be used to monitor and adjust the pressure swing adsorption process in real time, and the operating parameters can be adjusted according to the feedback information to ensure the stable operation of the system. Combined with the RTO algorithm, the operating strategy and parameters of the adsorption system are optimized and calculated to maximize the purity of hydrogen or minimize the production cost.

[0078] For example, in the pressure swing adsorption process, the APC algorithm is used to adjust the inlet pressure and permeate flow rate in real time, so that the hydrogen purity is increased from 85% to 90%, but there is still room for optimization. The RTO algorithm optimizes the calculation and determines the optimal operating parameters, so that the hydrogen purity reaches 95%, while reducing the production cost. In this way, the intelligent model constructed by combining the APC and RTO algorithms can realize intelligent optimization control of the pressure swing adsorption process.

[0079] In some embodiments, after obtaining the initial pressure swing adsorption time, the method further includes the following steps: obtaining multiple initial time periods, wherein the initial time period is a partial time period in the initial pressure swing adsorption time; obtaining a minimum initial time period among the multiple initial time periods; adjusting the minimum initial time period to increase the length of the minimum initial time period to obtain a first target time period, wherein the first target time period is a partial time period in the target pressure swing adsorption time.

[0080] In this scheme, if the pressure swing adsorption time is short, the adsorbent may fail to fully adsorb other gas components, the hydrogen purity cannot reach the expected target, the separation efficiency of the adsorbent will be affected, and high-purity hydrogen cannot be effectively separated. Therefore, the pressure swing adsorption time can be increased, which can further improve the hydrogen yield and further improve the quality of the product.

[0081] In some embodiments, after obtaining the initial pressure swing adsorption time, the method further includes the following steps: obtaining the maximum initial time period among the multiple initial time periods; adjusting the maximum initial time period to reduce the length of the maximum initial time period to obtain a second target time period, wherein the second target time period is a partial time period in the target pressure swing adsorption time.

[0082] In this scheme, if the pressure swing adsorption time is long, it may lead to energy waste and reduce production efficiency. The long pressure swing adsorption process will extend the production cycle and affect the production plan and product delivery time. Therefore, the duration of pressure swing adsorption can be reduced, which can further improve the hydrogen yield and further improve the quality of the product.

[0083] Specifically, the time allocation model mentioned above uses the set value of hydrogen quality and the feedback of the actual hydrogen purity deviation as the first control model to calculate and obtain the required time increment ΔT of 2S, 1S, -1S, and 2S. Then it is allocated to the corresponding T1-T9 time through the expert model.

[0084] The principle of the specific allocation model is as follows: Since the switching times of the program-controlled valves T1 (2 seconds), T5 (2 seconds), and T9 (2 seconds) are fixed, the time can be only allocated to T2 (6 seconds), T3 (7 seconds), T4 (7 seconds), T6 (6 seconds), T7 (7 seconds), and T8 (7 seconds).

[0085] First, compare the sums of T2 + T3 + T4 = ADD1 and T6 + T7 + T8 = ADD2 in groups. Thus, there are three cases: ADD1 = ADD2, ADD1 > ADD2, and ADD1 < ADD2.

[0086] Then, sequentially determine the maximum time Max1T and the minimum time Min1T of T2, T3, and T4, and the maximum time Max2T and the minimum time Min2T of T6, T7, and T8. When the time increment ΔT is positive, it is added to Min1T or Min2T, and vice versa.

[0087] When ADD1 = ADD2 and ΔT is 2, -2, 1, or -1 respectively:

[0088] When ΔT is 2 or 1, then add ΔT to the smaller of Min1T or Min2T of the two groups;

[0089] When ΔT is -2 or -1, then subtract ΔT from the larger of Max1T or Max2T of the two groups.

[0090] When ADD1 > ADD2 and ΔT is 2, -2, 1, or -1 respectively:

[0091] When ΔT is 2 or 1, then add ΔT to the smaller of Min1T or Min2T of the two groups;

[0092] When ΔT is -2 or -1, then subtract ΔT from the larger of Max1T or Max2T of the two groups.

[0093] When ADD1 < ADD2 and ΔT is 2, -2, 1, or -1 respectively:

[0094] When ΔT is 2 or 1, then add ΔT to the smaller of Min1T or Min2T of the two groups;

[0095] When ΔT is -2 or -1, then subtract ΔT from the larger of Max1T or Max2T of the two groups.

[0096] The time increment ΔT is limited by upper and lower limits in the pre-control module. And an output speed limit is added to the model, which changes once every 30 minutes. Compared with the existing DCS control, the safety of the PSA system is greatly guaranteed. The specific relationship between time and PSA steps is shown in Table 1.

[0097] Table 1

[0098]

[0099]

[0100]

[0101] The influence of each step process on hydrogen yield and quality and the time constant T1-T9. The PSA steps are: adsorption, average drop 1-7, forward release 1-2, reverse release 1-2, flushing 1-2, average rise 1-7, final flushing; the execution time of each step is as follows:

[0102] Adsorption time: the sum of T1+T2+T3+T4+T5+T6+T7+T8+T9;

[0103] All decreased by 1: the sum of T2+T3;

[0104] Both decreased by 2: the sum of T7+T8;

[0105] All decreased by 3: the sum of T2+T3+T4;

[0106] All down 4: the sum of T7+T8;

[0107] All decreased by 5: the sum of T2+T3+T4;

[0108] All down 6: the sum of T7+T8;

[0109] All decreased by 7: the sum of T2+T3+T4;

[0110] Sequential 1: the sum of T6+T7;

[0111] Sequential 2: the sum of T8+T9;

[0112] Reverse 1: T2;

[0113] Reverse 2: the sum of T3+T4+T5;

[0114] Rinse 2a: sum of T6+T7;

[0115] Rinse 2b: the sum of T8+T9;

[0116] Rinse 2c: the sum of T1+T2+T3;

[0117] Flushing 1a: sum of T4+T5;

[0118] Rinse 1b: sum of T6+T7;

[0119] Rinse 1c: the sum of T8+T9;

[0120] All rise 7: the sum of T2+T3+T4;

[0121] Average upgrade 6: the sum of T7+T8;

[0122] All rise 5: the sum of T2+T3+T4;

[0123] All upgrades 4: the sum of T7+T8;

[0124] All rise 3: the sum of T2+T3+T4;

[0125] Average upgrade 2: the sum of T7+T8;

[0126] All increase by 1: the sum of T2+T3;

[0127] Final rush: the sum of T4+T5+T6+T7+T8+T9.

[0128] Specifically, the above adjustment strategies are as follows:

[0129] (1) The adsorption time directly affects the yield and quality of hydrogen. To increase the hydrogen yield, any value of T1-T9 can be increased. After the increase, the yield increases. The impact of quality is reflected after 2-3 rounds of adsorption. Therefore, the adjustment rate of the adsorption time parameter should be slow, with an interval of at least 30 minutes.

[0130] (2) The length of the average rise and fall time has little effect on the hydrogen yield and quality;

[0131] (3) The process gases of sequential release 1 and sequential release 2 are used for flushing. The duration is related to the amount of desorption gas. The longer the time, the more the amount of flushing gas from the buffer tank to the desorption gas, the lower the hydrogen yield and the higher the quality.

[0132] (4) The gas from the reverse 1 and reverse 2 processes directly enters the desorption gas. The longer the time, the more desorption gas there is, the lower the hydrogen yield and the higher the quality.

[0133] (5) The gas from flushing 2 and flushing 1 directly enters the desorption gas. The longer the time, the more desorption gas there is, the lower the hydrogen yield and the higher the quality.

[0134] (6) The current setting value of the final charging time is greater than the charging pressure requirement, and adjusting the final charging time has no effect on the process;

[0135] (7) Based on the above impact analysis, when adjusting the time parameters T1 to T9, while increasing the adsorption time, try to avoid extending the time of forward placement, reverse placement, and flushing.

[0136] Specifically, each adsorption tower sequentially undergoes the steps of adsorption (A), forward release (PP), multiple equalized pressure drops (ED), reverse release (D), evacuation (V), evacuation and flushing (VP), multiple equalized pressure increases (ER), and final filling (FR). The steps of each adsorption tower are staggered to achieve continuous, stable and standard operation of the entire device.

[0137] Adsorption: Adsorption refers to the process of separating hydrogen from the mixed gas by adsorbing it through a pressure swing adsorbent.

[0138] Average reduction: Average reduction means that during the adsorption process, the pressure is gradually reduced so that the hydrogen adsorbed in the adsorbent is gradually released.

[0139] Forward release: Forward release means discharging the released hydrogen out of the system downstream to ensure that the flow direction of hydrogen in the system is smooth.

[0140] Reverse placement: Reverse placement means reversing the direction of hydrogen flow after forward placement to ensure that the residual hydrogen in the adsorbent is completely discharged.

[0141] Flushing: Flushing means injecting clean gas or liquid into the system to flush out impurities and residual hydrogen in the adsorbent in preparation for the next round of adsorption operation.

[0142] Average increase: Average increase means that during the flushing process, the pressure in the system is gradually increased to restore the adsorption capacity of the adsorbent.

[0143] Final charging: Final charging means injecting hydrogen into the system again after completing the above steps, preparing for the next round of adsorption operation.

[0144] Through the cyclic operation of these steps, the continuous production of hydrogen by pressure swing adsorption can be achieved, thereby improving the output and purity of hydrogen.

[0145] In this solution, for the explanation of each of the above steps, please refer to CN 110252083 A.

[0146] In order to more accurately determine the target pressure swing adsorption time, after obtaining the initial pressure swing adsorption time, the method further includes the following steps: constructing a third determination model, wherein the third determination model is trained using multiple sets of training data through an APC algorithm, an RTO algorithm and an optimization algorithm, each set of training data in the multiple sets of training data includes a historical initial pressure swing adsorption time, a historical hydrogen purity difference, a historical target hydrogen purity, and a historical target pressure swing adsorption time corresponding to the historical initial pressure swing adsorption time, the historical hydrogen purity difference, and the historical target hydrogen purity, and the optimization algorithm at least includes a genetic algorithm and / or a particle swarm optimization algorithm; inputting the initial pressure swing adsorption time, the hydrogen purity difference and the target hydrogen purity into the third determination model to obtain the target pressure swing adsorption time corresponding to the initial pressure swing adsorption time, the hydrogen purity difference and the target hydrogen purity.

[0147] In this solution, the APC algorithm, RTO algorithm and optimization algorithm can be combined for machine learning training. Through the combination of algorithms, the pressure swing adsorption time can be monitored and adjusted in real time to maximize the hydrogen purity and product quality, and ensure that the product meets the quality standards. The APC algorithm and the RTO algorithm are comprehensively utilized, combined with the genetic algorithm and the particle swarm optimization algorithm to obtain the third determination model. The third determination model can be used to achieve intelligent optimization of the pressure swing adsorption time, further improve production efficiency, and further reduce energy consumption and production costs.

[0148] Specifically, the APC algorithm is used to monitor and control the pressure swing adsorption process in real time, and the operating parameters are adjusted to maintain the system operating within the target range, such as maintaining the hydrogen purity within a certain range. On the basis of the APC algorithm, the RTO algorithm is used to optimize the entire process, and the optimization calculation is performed based on the process model to determine the best operating strategy and parameter settings to maximize the hydrogen purity or minimize the production cost. Combined with the optimization algorithm (such as the genetic algorithm or the particle swarm optimization algorithm), the pressure swing adsorption time is optimized and adjusted to achieve the best hydrogen purity and production efficiency.

[0149] Specifically, the APC algorithm is used to monitor and adjust the operating parameters of the process in real time to ensure that the system operates within the set target range. The APC algorithm adjusts the operating variables through real-time feedback control to meet the set target requirements. The RTO algorithm is used to optimize the operating strategy and parameter settings in real time to achieve the best production effect. The RTO algorithm combines the process model and the optimization algorithm to determine the best operating strategy and parameter settings by optimizing the system. In the process of intelligent optimization control, optimization algorithms such as genetic algorithms or particle swarm optimization algorithms can be combined to optimize and adjust operating parameters to maximize system performance or achieve specific goals.

[0150] For example, in the pressure swing adsorption process, under the real-time control of the APC algorithm, the initial pressure swing adsorption time is 15 minutes and the hydrogen purity is 88%. After RTO algorithm optimization and genetic algorithm optimization, the optimal pressure swing adsorption time is determined to be 30 minutes, and the hydrogen purity is increased to 92%. In this way, by combining the APC algorithm, RTO algorithm and optimization algorithm, an intelligent model is constructed, which realizes the intelligent optimization control of the pressure swing adsorption process and improves the hydrogen purity and production efficiency.

[0151] Specifically, the APC algorithm is used to monitor and adjust the operating parameters of the process in real time to ensure that the system operates within the set target range. The APC algorithm adjusts the operating variables through real-time feedback control to meet the set target requirements. The RTO algorithm is used to optimize the operating strategy and parameter settings in real time to achieve the best production effect. The RTO algorithm combines the process model and the optimization algorithm to determine the best operating strategy and parameter settings by optimizing the system. In the process of intelligent optimization control, optimization algorithms such as genetic algorithms or particle swarm optimization algorithms can be combined to optimize and adjust operating parameters to maximize system performance or achieve specific goals.

[0152] In summary, in the optimization control of pressure swing adsorption time, this scheme takes the components of tail gas entering PSA (H2, N2, CH4, CO2, CO) as the optimization target, adopts the "double optimization" optimization control strategy, and obtains the optimal effective gas production through the optimization of operating parameters. The deep neural network technology and real-time rolling optimization technology are combined to establish and optimize the prediction model of PSA adsorption time. Accurately determine the PSA adsorption time. Improve the recovery rate of hydrogen.

[0153] The embodiments of the present application also provide a control device for pressure swing adsorption. It should be noted that the control device for pressure swing adsorption in the embodiments of the present application can be used to execute the control method for pressure swing adsorption provided in the embodiments of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0154] The following is an introduction to the pressure swing adsorption control device provided in the embodiments of the present application.

[0155] Figure 5 is a structural block diagram of a pressure swing adsorption control device according to an embodiment of the present application. Figure 5 As shown, the device comprises:

[0156] A first acquisition unit 10 is used to acquire a hydrogen purity difference, wherein the hydrogen purity difference is a difference between an actual hydrogen purity and a target hydrogen purity;

[0157] A determination unit 20, configured to determine a target pressure swing adsorption time by using an APC algorithm and an RTO algorithm at least according to the above hydrogen purity difference;

[0158] The control unit 30 is used to control the operation of the pressure swing adsorption device according to the target pressure swing adsorption time.

[0159] Through this embodiment, the time of pressure swing adsorption can be determined by combining the APC algorithm and the RTO algorithm. The APC algorithm is a multivariable optimization algorithm that can perform precise control and reduce errors. The RTO algorithm can be optimized in real time to ensure that the strategy remains in the optimal state. Therefore, the combination of the APC algorithm and the RTO algorithm can improve the accuracy of decision-making, thereby obtaining an accurate time for pressure swing adsorption, thereby improving the purity of the product and making the recovery rate more stable.

[0160] In order to further accurately determine the target hydrogen purity, the above-mentioned device also includes a second acquisition unit, a first construction unit and a first processing unit. The second acquisition unit is used to obtain relevant information before obtaining the hydrogen purity difference, wherein the above-mentioned relevant information includes one or more of the permeate gas flow rate, the intake pressure and the gas component; the first construction unit is used to construct a first determination model, wherein the above-mentioned first determination model is obtained by training using multiple groups of training data, and each group of training data in the above-mentioned multiple groups of training data includes historical relevant information obtained within a historical time period and the historical target hydrogen purity corresponding to the above-mentioned historical relevant information; the first processing unit is used to input the above-mentioned relevant information into the above-mentioned first determination model to obtain the above-mentioned target hydrogen purity corresponding to the above-mentioned relevant information.

[0161] In this scheme, machine learning training can be performed based on the permeate gas flow rate, intake pressure and gas composition to obtain a first determination model, and the first determination model can be used to more accurately determine the target hydrogen purity corresponding to the permeate gas flow rate, intake pressure and gas composition.

[0162] During the specific implementation process, the determination unit includes an acquisition module and a determination module. The acquisition module is used to acquire the initial pressure swing adsorption time; the determination module is used to determine the target pressure swing adsorption time according to the initial pressure swing adsorption time, the hydrogen purity difference and the target hydrogen purity, using the APC algorithm and the RTO algorithm.

[0163] In this solution, APC can be optimized and controlled to further solve the problem that the current pressure swing adsorption control adsorption regeneration time is manually set based on experience. Based on the precise and reliable control solution of APC+RTO, the adsorption time is obtained, the edge control of hydrogen quality is achieved, and the hydrogen recovery rate is further improved.

[0164] During the specific implementation process, the determination module includes a construction module and a processing module, the construction module is used to construct a second determination model, wherein the above-mentioned second determination model is obtained by training through the APC algorithm and the RTO algorithm using multiple groups of training data, and each group of training data in the above-mentioned multiple groups of training data includes historical initial pressure swing adsorption time, historical hydrogen purity difference, historical target hydrogen purity, and the historical target pressure swing adsorption time corresponding to the above-mentioned historical initial pressure swing adsorption time, the above-mentioned historical hydrogen purity difference, and the above-mentioned historical target hydrogen purity; the processing module is used to input the above-mentioned initial pressure swing adsorption time, the above-mentioned hydrogen purity difference and the above-mentioned target hydrogen purity into the above-mentioned second determination model to obtain the above-mentioned initial pressure swing adsorption time, the above-mentioned hydrogen purity difference and the above-mentioned target pressure swing adsorption time corresponding to the above-mentioned target hydrogen purity.

[0165] In this scheme, the APC algorithm is a multivariable optimization algorithm that can perform precise control and reduce errors. The RTO algorithm can perform real-time optimization to ensure that the strategy remains in the optimal state. Therefore, this scheme adopts a combination of the APC algorithm and the RTO algorithm to perform machine learning training to obtain a second determination model. The second determination model can be used to more accurately determine the target pressure swing adsorption time.

[0166] In some embodiments, the device further includes a third acquisition unit, a fourth acquisition unit and a second processing unit, the third acquisition unit being used to acquire multiple initial time periods after acquiring the initial pressure swing adsorption time, wherein the initial time period is a partial time period in the initial pressure swing adsorption time; the fourth acquisition unit being used to acquire the minimum initial time period among the multiple initial time periods; and the second processing unit being used to adjust the minimum initial time period, increasing the length of the minimum initial time period, and obtaining a first target time period, wherein the first target time period is a partial time period in the target pressure swing adsorption time.

[0167] In this scheme, if the pressure swing adsorption time is short, the adsorbent may fail to fully adsorb other gas components, the hydrogen purity cannot reach the expected target, the separation efficiency of the adsorbent will be affected, and high-purity hydrogen cannot be effectively separated. Therefore, the pressure swing adsorption time can be increased, which can further improve the hydrogen yield and further improve the quality of the product.

[0168] In some embodiments, the above-mentioned device also includes a fifth acquisition unit and a third processing unit. The fifth acquisition unit is used to obtain the maximum initial time period among the multiple initial time periods after obtaining the initial pressure swing adsorption time; the third processing unit is used to adjust the above-mentioned maximum initial time period, reduce the length of the above-mentioned maximum initial time period, and obtain a second target time period, wherein the above-mentioned second target time period is a partial time period in the above-mentioned target pressure swing adsorption time.

[0169] In this scheme, if the pressure swing adsorption time is long, it may lead to energy waste and reduce production efficiency. The long pressure swing adsorption process will extend the production cycle and affect the production plan and product delivery time. Therefore, the duration of pressure swing adsorption can be reduced, which can further improve the hydrogen yield and further improve the quality of the product.

[0170] In order to more accurately determine the target pressure swing adsorption time, the above-mentioned device also includes a second construction unit and a fourth processing unit. The second construction unit is used to construct a third determination model after obtaining the initial pressure swing adsorption time, wherein the above-mentioned third determination model is obtained by training through an APC algorithm, an RTO algorithm and an optimization algorithm using multiple sets of training data, each set of training data in the above-mentioned multiple sets of training data includes a historical initial pressure swing adsorption time, a historical hydrogen purity difference, and a historical target hydrogen purity, and the historical target pressure swing adsorption time corresponding to the above-mentioned historical initial pressure swing adsorption time, the above-mentioned historical hydrogen purity difference, and the above-mentioned historical target hydrogen purity, and the above-mentioned optimization algorithm at least includes a genetic algorithm and / or a particle swarm optimization algorithm; the fourth processing unit is used to input the above-mentioned initial pressure swing adsorption time, the above-mentioned hydrogen purity difference and the above-mentioned target hydrogen purity into the above-mentioned third determination model to obtain the above-mentioned initial pressure swing adsorption time, the above-mentioned hydrogen purity difference and the above-mentioned target hydrogen purity corresponding to the above-mentioned target pressure swing adsorption time.

[0171] In this solution, the APC algorithm, RTO algorithm and optimization algorithm can be combined for machine learning training. Through the combination of algorithms, the pressure swing adsorption time can be monitored and adjusted in real time to maximize the hydrogen purity and product quality, and ensure that the product meets the quality standards. The APC algorithm and the RTO algorithm are comprehensively utilized, combined with the genetic algorithm and the particle swarm optimization algorithm to obtain the third determination model. The third determination model can be used to achieve intelligent optimization of the pressure swing adsorption time, further improve production efficiency, and further reduce energy consumption and production costs.

[0172] The pressure swing adsorption control device includes a processor and a memory. The first acquisition unit, the determination unit and the control unit are stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0173] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters can be adjusted to solve the problem of low accuracy of pressure swing adsorption time in the prior art, resulting in low purity of product gas and unstable yield.

[0174] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0175] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the pressure swing adsorption control method.

[0176] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the pressure swing adsorption control method is executed when the program is run.

[0177] An embodiment of the present invention provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, at least steps of a pressure swing adsorption control method are implemented.

[0178] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0179] A computer program product includes a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the pressure swing adsorption control method in each embodiment of the present application are implemented.

[0180] The present application also provides a pressure swing adsorption control system, comprising one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a control method for executing any one of the above-mentioned pressure swing adsorption.

[0181] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0182] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0183] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0184] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0185] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0186] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0187] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0188] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0189] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0190] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0191] 1) The pressure swing adsorption control method of the present application can use a combination of the APC algorithm and the RTO algorithm to determine the time of the pressure swing adsorption. The APC algorithm is a multivariable optimization algorithm that can perform precise control and reduce errors. The RTO algorithm can be optimized in real time to ensure that the strategy remains in the optimal state. Therefore, the combination of the APC algorithm and the RTO algorithm can improve the accuracy of decision-making, thereby obtaining an accurate time for the pressure swing adsorption, thereby improving the purity of the product and making the recovery rate more stable.

[0192] 2) The pressure swing adsorption control device of the present application can use a combination of the APC algorithm and the RTO algorithm to determine the time of the pressure swing adsorption. The APC algorithm is a multivariable optimization algorithm that can perform precise control and reduce errors. The RTO algorithm can be optimized in real time to ensure that the strategy remains in the optimal state. Therefore, the combination of the APC algorithm and the RTO algorithm can improve the accuracy of decision-making, thereby obtaining an accurate time for the pressure swing adsorption, thereby improving the purity of the product and making the recovery rate more stable.

[0193] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A pressure swing adsorption control method, characterized in that: include: Obtaining a hydrogen purity difference, wherein the hydrogen purity difference is a difference between an actual hydrogen purity and a target hydrogen purity; Determining a target pressure swing adsorption time using an APC algorithm and an RTO algorithm at least according to the hydrogen purity difference; The operation of the pressure swing adsorption device is controlled according to the target pressure swing adsorption time.

2. The method according to claim 1, characterized in that: Before obtaining the hydrogen purity difference, the method further includes: Acquiring relevant information, wherein the relevant information includes one or more of permeate gas flow rate, inlet pressure and gas composition; Constructing a first determination model, wherein the first determination model is obtained by training using multiple sets of training data, each set of training data in the multiple sets of training data includes historical relevant information obtained within a historical time period and a historical target hydrogen purity corresponding to the historical relevant information; The relevant information is input into the first determination model to obtain the target hydrogen purity corresponding to the relevant information.

3. The method according to claim 1, characterized in that: At least according to the hydrogen purity difference, the target pressure swing adsorption time is determined by using the APC algorithm and the RTO algorithm, including: Obtaining initial pressure swing adsorption time; The target pressure swing adsorption time is determined by adopting an APC algorithm and an RTO algorithm according to the initial pressure swing adsorption time, the hydrogen purity difference and the target hydrogen purity.

4. The method according to claim 3, characterized in that According to the initial pressure swing adsorption time, the hydrogen purity difference and the target hydrogen purity, the target pressure swing adsorption time is determined by using an APC algorithm and an RTO algorithm, including: Constructing a second determination model, wherein the second determination model is obtained by training with an APC algorithm and an RTO algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes a historical initial pressure swing adsorption time, a historical hydrogen purity difference, and a historical target hydrogen purity, and the historical initial pressure swing adsorption time, the historical hydrogen purity difference, and the historical target pressure swing adsorption time corresponding to the historical target hydrogen purity; The initial pressure swing adsorption time, the hydrogen purity difference and the target hydrogen purity are input into the second determination model to obtain the target pressure swing adsorption time corresponding to the initial pressure swing adsorption time, the hydrogen purity difference and the target hydrogen purity.

5. The method according to claim 3, characterized in that: After obtaining the initial pressure swing adsorption time, the method further includes: Acquire multiple initial time periods, wherein the initial time period is a partial time period of the initial pressure swing adsorption time; Obtaining a minimum initial time period among the multiple initial time periods; The minimum initial time period is adjusted to increase the length of the minimum initial time period to obtain a first target time period, wherein the first target time period is a partial time period of the target pressure swing adsorption time.

6. The method according to claim 5, characterized in that After obtaining the initial pressure swing adsorption time, the method further includes: Obtaining a maximum initial time period among the multiple initial time periods; The maximum initial time period is adjusted to reduce the length of the maximum initial time period to obtain a second target time period, wherein the second target time period is a partial time period of the target pressure swing adsorption time.

7. The method according to claim 3, characterized in that After obtaining the initial pressure swing adsorption time, the method further includes: Constructing a third determination model, wherein the third determination model is obtained by training with multiple sets of training data through an APC algorithm, an RTO algorithm, and an optimization algorithm, each set of training data in the multiple sets of training data includes a historical initial pressure swing adsorption time, a historical hydrogen purity difference, and a historical target hydrogen purity, the historical initial pressure swing adsorption time, the historical hydrogen purity difference, and the historical target pressure swing adsorption time corresponding to the historical target hydrogen purity, and the optimization algorithm includes at least a genetic algorithm and / or a particle swarm optimization algorithm; The initial pressure swing adsorption time, the hydrogen purity difference and the target hydrogen purity are input into the third determination model to obtain the target pressure swing adsorption time corresponding to the initial pressure swing adsorption time, the hydrogen purity difference and the target hydrogen purity.

8. A pressure swing adsorption control device, characterized in that: include: A first acquisition unit is used to acquire a hydrogen purity difference, wherein the hydrogen purity difference is a difference between an actual hydrogen purity and a target hydrogen purity; A determination unit, configured to determine a target pressure swing adsorption time by using an APC algorithm and an RTO algorithm at least according to the hydrogen purity difference; The control unit is used to control the operation of the pressure swing adsorption device according to the target pressure swing adsorption time.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the pressure swing adsorption control method according to any one of claims 1 to 7 are implemented.

10. A pressure swing adsorption control system, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the pressure swing adsorption control method according to any one of claims 1 to 7.

Images